Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 745 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 2.9518. Min Range: -2.9518
Max Act: 2.9518. Min Act: -0.1700
Data Index: 5418804 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9518. Min Range: -2.9518
Max Act: 2.9359. Min Act: -0.1700
Data Index: 6152803 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9518. Min Range: -2.9518
Max Act: 2.9043. Min Act: -0.1700
Data Index: 1274739 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9518. Min Range: -2.9518
Max Act: 2.9043. Min Act: -0.1700
Data Index: 8575331 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9518. Min Range: -2.9518
Max Act: 2.8884. Min Act: -0.1700
Data Index: 4555227 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9518. Min Range: -2.9518
Max Act: 2.8884. Min Act: -0.1700
Data Index: 2283790 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9518. Min Range: -2.9518
Max Act: 2.8884. Min Act: -0.1700
Data Index: 6154412 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9518. Min Range: -2.9518
Max Act: 2.8725. Min Act: -0.1700
Data Index: 6890908 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9518. Min Range: -2.9518
Max Act: 2.8566. Min Act: -0.1700
Data Index: 2283710 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9518. Min Range: -2.9518
Max Act: 2.8884. Min Act: -0.1700
Data Index: 848139 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9518. Min Range: -2.9518
Max Act: 2.8566. Min Act: -0.1700
Data Index: 7254222 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9518. Min Range: -2.9518
Max Act: 2.8566. Min Act: -0.1700
Data Index: 4469250 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9518. Min Range: -2.9518
Max Act: 2.8566. Min Act: -0.1700
Data Index: 6473053 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9518. Min Range: -2.9518
Max Act: 2.8408. Min Act: -0.1700
Data Index: 6318799 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9518. Min Range: -2.9518
Max Act: 2.8408. Min Act: -0.1700
Data Index: 1665225 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9518. Min Range: -2.9518
Max Act: 2.8566. Min Act: -0.1700
Data Index: 1484258 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9518. Min Range: -2.9518
Max Act: 2.8725. Min Act: -0.1700
Data Index: 3125381 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9518. Min Range: -2.9518
Max Act: 2.8566. Min Act: -0.1700
Data Index: 6134062 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9518. Min Range: -2.9518
Max Act: 2.8408. Min Act: -0.1700
Data Index: 4898302 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9518. Min Range: -2.9518
Max Act: 2.8408. Min Act: -0.1700
Data Index: 3055483 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19